lead-qualification

Lead qualification engine with conversational intake. Asks structured questions to understand your qualification criteria, generates a reusable qualification prompt, then batch-enriches leads via Apify LinkedIn scraping and scores them with parallel processing. Outputs qualified/disqualified verdicts with confidence scores and reasoning to CSV or whatever output format the user prefers. Supports calibration mode for prompt refinement.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced workflow document with genuine validation feedback loops for its batch operations. Its weaknesses are repetition of the enrichment-fallback guidance across multiple steps and heavy inlining of the prompt template and intake question bank that would be better split into reference files.

Suggestions

State the enrichment-fallback rule ('web search only when enrichment_status is failed or no_url') once and reference it from the other steps instead of repeating it four times.

Move the qualification-prompt template and the full intake question bank into a references/ file (e.g. references/prompt-template.md and references/intake-questions.md), keeping SKILL.md as a lean overview.

Trim promotional phrasing ('MUCH faster and cheaper', 'dramatically improving speed and consistency') in favor of plain factual statements.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — the intake questions, prompt template, and parallelization protocol are content Claude cannot infer — but the enrichment-fallback rule is repeated four times (Step 1.5, Step 2, batch inputs, per-lead processing) and marketing phrasing like 'MUCH faster and cheaper' and 'dramatically improving speed and consistency' could be trimmed.	3 / 5
Actionability	Guidance is fully executable: a copy-paste bash command with flags and --dry-run, exact enriched column names, exact calibration table and summary formats, a concrete batching protocol (15 leads/batch, 2-10 batches, retry once), and worked example invocations for all three modes.	5 / 5
Workflow Clarity	The multi-phase sequence is explicit with real validation checkpoints and feedback loops for a batch operation: a calibration batch repeated 'until the user approves', a completeness count check (qualified + disqualified + failed = total), and failed-batch retry with re-processing of missing leads.	5 / 5
Progressive Disclosure	Section structure is clear and the one bundle reference (scripts/enrich_leads.py, which exists in the bundle) is clearly signaled with its command, but the ~60-line qualification-prompt template and the 20-question intake bank are inlined in a 360-line SKILL.md where a references/ split would keep the overview lean.	3 / 5
	Total	16 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, concrete, and distinctive description that clearly communicates what the skill does across all its phases. Its main weakness is the complete absence of a 'when to use' trigger clause, which both caps completeness and leaves trigger-term coverage thinner than it could be.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to qualify leads, score prospects, or filter a lead list against custom criteria.'

Include natural synonyms users would say, such as 'prospects', 'lead scoring', 'lead list', and 'outbound campaign', to improve trigger matching.

State the input expectation (a CSV or list of LinkedIn profiles) in the description so users know what to provide upfront.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Asks structured questions', 'generates a reusable qualification prompt', 'batch-enrichs leads via Apify LinkedIn scraping', 'scores them with parallel processing', 'Outputs qualified/disqualified verdicts with confidence scores and reasoning to CSV' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clearly and concretely answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('lead qualification', 'qualify', 'leads', 'LinkedIn', 'CSV'), but common synonyms users would say — 'prospects', 'lead scoring', 'sales pipeline', 'outbound' — are missing, so it falls short of the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	'Lead qualification engine' with Apify LinkedIn enrichment and qualification-prompt calibration is a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gooseworks-ai/goose-skills
Path: skills/lead-generation/capabilities/lead-qualification/SKILL.md
Commit: cc3e518

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.